© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 30-TRANSCODER-HP
    7. 94884
    Prev
    Next
    INDEX
    Explanations

    tax

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    iability
    -0.32
    editable
    -0.29
     editable
    -0.28
     treat
    -0.27
    ActionResult
    -0.27
    reat
    -0.26
     traded
    -0.26
     classified
    -0.26
    imately
    -0.26
    akov
    -0.25
    POSITIVE LOGITS
    éķij
    0.30
    offs
    0.28
     zb
    0.28
    öl
    0.28
    æ§Ľ
    0.27
    	unit
    0.27
    [unit
    0.26
    unit
    0.26
    opers
    0.26
    _CALLBACK
    0.25
    Activations Density 0.002%

    No Known Activations